Skip to content

Cov integ 2 #14

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
juli-p wants to merge 16 commits into
base: main
Choose a base branch
from
Draft

Cov integ 2 #14

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
16 commits
Select commit Hold shift + click to select a range
bfe2473
classic missing ;
maximus-victor Jul 13, 2023
9b2144a
cov push w req errors
maximus-victor Aug 5, 2023
e0ba0bc
integrated covariate calculation into NeEDL pipeline
juli-p Aug 6, 2023
ab09e02
readme up
maximus-victor Aug 6, 2023
736e4db
readme up
maximus-victor Aug 7, 2023
81cab8f
removed -max-itrs flag, started implementing unit test for NaN
juli-p Aug 16, 2023
822b30e
Merge branch 'cov_integ_2' of https://github.com/biomedbigdata/NeEDL …
juli-p Aug 16, 2023
1fc0e85
tried to get cov working in NeEDL workflow
juli-p Oct 2, 2023
1c39037
Merge branch 'main' into cov_integ_2
juli-p Oct 2, 2023
ed2e933
added nan e2e test
juli-p Oct 2, 2023
a42d1e9
fixed docker container bug in e2e test
juli-p Oct 2, 2023
e1924ee
added --covariates-file to mount list
juli-p Oct 2, 2023
3153e34
e2e test more verbose
juli-p Oct 2, 2023
de681ae
e2e bug fix
juli-p Oct 2, 2023
2bb3093
continue searching the error
juli-p Oct 2, 2023
395823e
cleaning up
juli-p Nov 8, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 9 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -357,6 +357,15 @@ NeEDL supports various statistical scores that can be used for `--ms-model`. Ple
- `REGRESSION_LLH_GAIN`: likelihood gain of the quadratic-regression model
- `REGRESSION_AIC_GAIN`: Akaike information criterion gain of the quadratic-regression model
- `REGRESSION_BIC_GAIN`: Bayesian information criterion gain of the quadratic-regression model
- `REGRESSION_COV_NLL`: negative log-likelihood of the quadratic-regression model, includes covariates
- `REGRESSION_COV_LLH`: likelihood of the quadratic-regression model, includes covariates
- `REGRESSION_COV_AIC`: Akaike information criterion of the quadratic-regression model, includes covariates
- `REGRESSION_COV_BIC`: Bayesian information criterion of the quadratic-regression model, includes covariates
- `REGRESSION_CLG_Q_LC`: Confounder corrected likelihood gain (CLG) of linear regression model vs linear regression model with covariates. We define CLG as the LLH-Gain of a model with covariates over a model without covariates. The higher the CLG, the better is our linear model with covariates.
- `REGRESSION_CLG_Q_QC`: Confounder corrected likelihood gain (CLG) of quadratic regression model vs quadratic regression model with covariates. We define CLG as the LLH-Gain of a model with covariates over a model without covariates. The higher the CLG, the better is our quadratic model with covariates.
- `REGRESSION_CLG_L_LC`: Confounder corrected likelihood gain (CLG) of  quadratic regression model vs linear regression model with covariates. We define CLG as the LLH-Gain of a model with covariates over a model without covariates. The higher the CLG, the better is our linear model with covariates.

**IMPORTANT: Please make sure you selected a score that has `COV` in its name if you want to use covariates. Specifying a covariate file is not enough.**

Options for the annealing type are `SIMULATED_ANNEALING`, `RANDOM_ANNEALING`, `HYPERBOLIC_TAN_ANNEALING`.

Expand Down
Loading